SKILLEMALL.ai
GitHub ↗ RU Sign in

AB pendle-pt-yield-strategy

Pendle PT fixed-yield strategy for market scanning, ranking, position tracking, maturity monitoring, and execution planning. Prefer managed wallet execution through Privy or a similar policy-controlled wallet backend, and otherwise fall back to manual user-executed transactions. Use when the user wants to research Pendle PT opportunities, choose stable-ish PT markets, monitor active PT positions, or prepare Pendle PT deposit, redeem, withdraw, and rollover actions with explicit confirmation and clear wallet-path disclosures.

ClawHub Agent Skills author: Moshu v1.0.2 MIT-0 23 files body ≈ 2 855 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process B 69/100 · Nearly there — weak spots: result and completion, inputs and preconditions, progress reporting

ProcedureInfrastructureSoftware developmenttype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
A
90/100
safety, quality, tests
Safety 60%
94
Quality 40%
85
Run on models
none yet
Process rating
B
69/100
Nearly there
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

How to improve

    For the model run — optional
    • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
    • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

    Guard findings · 6

    ✓ No critical or high findings

    Medium and low: 6
    • low Secrets in code secret-high-entropy-token references/chain-addresses.md:5
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      - Ethereum: `0xA0…B48`
      quoted
    • low Secrets in code secret-high-entropy-token references/chain-addresses.md:6
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      - Arbitrum: `0xaf…831`
      quoted
    • low Secrets in code secret-high-entropy-token references/chain-addresses.md:7
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      - Base: `0x83…913`
      quoted
    • low Secrets in code secret-high-entropy-token scripts/check-slippage.py:26
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      1:     "0xA0…B48",
      quoted
    • low Secrets in code secret-high-entropy-token scripts/check-slippage.py:27
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      42161: "0xaf…831",
      quoted
    • low Secrets in code secret-high-entropy-token scripts/check-slippage.py:28
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      8453:  "0x83…913",
      quoted

    Files scanned: 23. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 69/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Progress reporting. Says nothing while it works
    • 70When it triggers. States when to use, but not when not to
    • 100Tools and files. No external tools needed
    • 100Steps. 107 steps
    • 100Failures and branches. 4 branches, has a failure section
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 2855 tokens
    • 100Running it twice. Mutating operations check current state
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
    • low 13 top-level sections: this looks like several domains in one skill

    Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

    Quality signals

    • +5Description has no quoted example phrases that should trigger the skill
    • +4Description does not say when NOT to use the skill (false activations)
    • +3Output format is not stated: the model decides each time
    • -39 of 15 scripts are never mentioned in SKILL.md
    • +1No license
    • +2Single-language instructions
    • +3Description length 530: enough signal without eating the budget
    • +4Structure: 31 headings
    • +3Step-by-step instructions: 107 items
    • +4Has examples (2 code blocks)
    • +4Reference files are cited in the instructions (2 of 4)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.

    External checks

    ClawHub: clean
    This skill is a disclosed DeFi research and planning aid that scans public Pendle-related markets and avoids bundled private-key signing or automatic transaction submission.
    LLM: benign (high) · 28 May 2026